Generalize tracker references, restructure refactor skill, and strengthen coding rules

- Replace all Jira-specific references with generic tracker/work-item
  terminology (TRACKER-ID, work item epics); delete project-management.mdc
  and mcp.json.example
- Restructure refactor skill: extract 8 phases (00–07) and templates into
  separate files; add guided mode for pre-built change lists
- Add Step 3 "Code Testability Revision" to existing-code workflow
  (renumber steps 3–12 → 3–13)
- Simplify autopilot state file to minimal current-step pointer
- Strengthen coding rules: AAA test comments per language, test failures as
  blocking gates, dependency install policy
- Add Docker Suitability Assessment to test-spec and test-run skills
  (local vs Docker execution)
- Narrow human-attention sound rule to human-input-needed only
- Add AskQuestion fallback to plain text across skills
- Rename FINAL_implementation_report to implementation_report_*
- Simplify cursor-meta (remove _docs numbering table, quality thresholds)
- Make techstackrule alwaysApply, add alwaysApply:false to openapi

.cursor/skills/plan/steps/06_work-item-epics.md

@@ -0,0 +1,48 @@
+## Step 6: Work Item Epics
+
+**Role**: Professional product manager
+
+**Goal**: Create epics from components, ordered by dependency
+
+**Constraints**: Epic descriptions must be **comprehensive and self-contained** — a developer reading only the epic should understand the full context without needing to open separate files.
+
+1. **Create "Bootstrap & Initial Structure" epic first** — this epic will parent the `01_initial_structure` task created by the decompose skill. It covers project scaffolding: folder structure, shared models, interfaces, stubs, CI/CD config, DB migrations setup, test structure.
+2. Generate epics for each component using the configured work item tracker (see `autopilot/protocols.md` for tracker detection), structured per `templates/epic-spec.md`
+3. Order epics by dependency (Bootstrap epic is always first, then components based on their dependency graph)
+4. Include effort estimation per epic (T-shirt size or story points range)
+5. Ensure each epic has clear acceptance criteria cross-referenced with component specs
+6. Generate Mermaid diagrams showing component-to-epic mapping and component relationships
+
+**CRITICAL — Epic description richness requirements**:
+
+Each epic description MUST include ALL of the following sections with substantial content:
+- **System context**: where this component fits in the overall architecture (include Mermaid diagram showing this component's position and connections)
+- **Problem / Context**: what problem this component solves, why it exists, current pain points
+- **Scope**: detailed in-scope and out-of-scope lists
+- **Architecture notes**: relevant ADRs, technology choices, patterns used, key design decisions
+- **Interface specification**: full method signatures, input/output types, error types (from component description.md)
+- **Data flow**: how data enters and exits this component (include Mermaid sequence or flowchart diagram)
+- **Dependencies**: epic dependencies (with tracker IDs) and external dependencies (libraries, hardware, services)
+- **Acceptance criteria**: measurable criteria with specific thresholds (from component tests.md)
+- **Non-functional requirements**: latency, memory, throughput targets with failure thresholds
+- **Risks & mitigations**: relevant risks from risk_mitigations.md with concrete mitigation strategies
+- **Effort estimation**: T-shirt size and story points range
+- **Child issues**: planned task breakdown with complexity points
+- **Key constraints**: from restrictions.md that affect this component
+- **Testing strategy**: summary of test types and coverage from tests.md
+
+Do NOT create minimal epics with just a summary and short description. The epic is the primary reference document for the implementation team.
+
+**Self-verification**:
+- [ ] "Bootstrap & Initial Structure" epic exists and is first in order
+- [ ] "Blackbox Tests" epic exists
+- [ ] Every component maps to exactly one epic
+- [ ] Dependency order is respected (no epic depends on a later one)
+- [ ] Acceptance criteria are measurable
+- [ ] Effort estimates are realistic
+- [ ] Every epic description includes architecture diagram, interface spec, data flow, risks, and NFRs
+- [ ] Epic descriptions are self-contained — readable without opening other files
+
+7. **Create "Blackbox Tests" epic** — this epic will parent the blackbox test tasks created by the `/decompose` skill. It covers implementing the test scenarios defined in `tests/`.
+
+**Save action**: Epics created via the configured tracker MCP. Also saved locally in `epics.md` with ticket IDs. If `tracker: local`, save locally only.